Co-Locating Style-Defining Elements on 3D Shapes

This work was supported in part by NSFC (Grants No. 61602311, No. 61522213, and No. 61528208), 973 Program (Grant No. 2015CB352501), Guangdong Science and Technology Program (Grants No. 2014TX01X033, No. 2015A030312015, and No. 2016A050503036), Shenzhen Innovation Program (Grant No. JCYJ20151015151249564), Natural Science Foundation of SZU (Grant No. 827-000196), and NSERC (Grants No. 611370 and No. 2015-05407). Authors’ addresses: R. Hu and W. Li, College of Computer Science & Software Engineering, Shenzhen University, 821 CSSE Building, 3688 Nanhai Ave., Shenzhen, Guangdong, 518060, P.R. China; emails: {ruizhen.hu, manchiu.lee.9}@gmail.com; O. van Kaick, School of Computer Science, Carleton University, 5302 Herzberg Building, 1125 Colonel By Drive, Ottawa, ON, K1S 5B6, Canada; email: Oliver.vanKaick@carleton.ca; H. Huang (corresponding author), College of Computer Science & Software Engineering, Shenzhen University, 839 CSSE Building, 3688 Nanhai Ave., Shenzhen, Guangdong, 518060, P.R. China; email: hhzhiyan@gmail.com; M. Averkiou, Dept. of Computer Science, University of Cyprus, 1 University Avenue, Building FFT01, room B107, Nicosia 1678, Cyprus; email: melinos.averkiou@gmail.com; D. Cohen-Or, School of Computer Science, Tel Aviv University, Schreiber Building, room 216, Tel Aviv 69978, Israel; email: dcor@tau.ac.il; H. Zhang, School of Computing Science, Simon Fraser University, 8027 TASC I, 8888 University Drive, Burnaby, BC, V5A 1S6, Canada; email: haoz@cs.sfu.ca. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies show this notice on the first page or initial screen of a display along with the full citation. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, to redistribute to lists, or to use any component of this work in other works requires prior specific permission and/or a fee. Permissions may be requested from Publications Dept., ACM, Inc., 2 Penn Plaza, Suite 701, New York, NY 10121-0701 USA, fax +1 (212) 869-0481, or permissions@acm.org. c © 2017 ACM 0730-0301/2017/06-ART33 $15.00 DOI: http://dx.doi.org/10.1145/3092817 We introduce a method for co-locating style-defining elements over a set of 3D shapes. Our goal is to translate high-level style descriptions, such as “Ming” or “European” for furniture models, into explicit and localized regions over the geometric models that characterize each style. For each style, the set of style-defining elements is defined as the union of all the elements that are able to discriminate the style. Another property of the style-defining elements is that they are frequently occurring, reflecting shape characteristics that appear across multiple shapes of the same style. Given an input set of 3D shapes spanning multiple categories and styles, where the shapes are grouped according to their style labels, we perform a cross-category co-analysis of the shape set to learn and spatially locate a set of defining elements for each style. This is accomplished by first sampling a large number of candidate geometric elements and then iteratively applying feature selection to the candidates, to extract style-discriminating elements until no additional elements can be found. Thus, for each style label, we obtain sets of discriminative elements that together form the superset of defining elements for the style. We demonstrate that the co-location of style-defining elements allows us to solve problems such as style classification, and enables a variety of applications such as style-revealing view selection, style-aware sampling, and style-driven modeling for 3D shapes.

[1]  David W. Jacobs,et al.  Mesh saliency , 2005, ACM Trans. Graph..

[2]  Alexei A. Efros,et al.  What makes Paris look like Paris? , 2015, Commun. ACM.

[3]  Marc Alexa,et al.  The Markov pen: online synthesis of free-hand drawing styles , 2015, NPAR '15.

[4]  Eric Fernie,et al.  Art History and Its Methods: A Critical Anthology , 1995 .

[5]  Yong Jae Lee,et al.  Style-Aware Mid-level Representation for Discovering Visual Connections in Space and Time , 2013, 2013 IEEE International Conference on Computer Vision.

[6]  Wilmot Li,et al.  Style compatibility for 3D furniture models , 2015, ACM Trans. Graph..

[7]  Nuria Oliver,et al.  Curve Analogies , 2002, Rendering Techniques.

[8]  Alla Sheffer,et al.  Analogy‐driven 3D style transfer , 2014, Comput. Graph. Forum.

[9]  Denis Simakov,et al.  Summarizing visual data using bidirectional similarity , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Paolo Cignoni,et al.  Ieee Transactions on Visualization and Computer Graphics 1 Efficient and Flexible Sampling with Blue Noise Properties of Triangular Meshes , 2022 .

[11]  Ayellet Tal,et al.  Saliency Detection in Large Point Sets , 2013, 2013 IEEE International Conference on Computer Vision.

[12]  Y. Wang,et al.  Curve Style Analysis in a Set of Shapes , 2013, Comput. Graph. Forum.

[13]  Joshua B. Tenenbaum,et al.  Learning style translation for the lines of a drawing , 2003, TOGS.

[14]  S. Avidan,et al.  Seam carving for content-aware image resizing , 2007, SIGGRAPH 2007.

[15]  Alla Sheffer,et al.  Functionality preserving shape style transfer , 2016, ACM Trans. Graph..

[16]  Remco C. Veltkamp,et al.  A survey of content based 3D shape retrieval methods , 2004, Proceedings Shape Modeling Applications, 2004..

[17]  Diego Gutierrez,et al.  A similarity measure for illustration style , 2014, ACM Trans. Graph..

[18]  Alexander M. Bronstein,et al.  Supervised learning of bag‐of‐features shape descriptors using sparse coding , 2014, Comput. Graph. Forum.

[19]  Ariel Shamir,et al.  Style and abstraction in portrait sketching , 2013, ACM Trans. Graph..

[20]  Aaron Hertzmann,et al.  Exploratory font selection using crowdsourced attributes , 2014, ACM Trans. Graph..

[21]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[22]  D. Cohen-Or,et al.  Style-content separation by anisotropic part scales , 2010, ACM Trans. Graph..

[23]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Alla Sheffer,et al.  Elements of style , 2015, ACM Trans. Graph..

[25]  Mark W. Schmidt,et al.  Fast Optimization Methods for L1 Regularization: A Comparative Study and Two New Approaches , 2007, ECML.

[26]  S. Pandya.  Style. , 1987 .

[27]  Andrea Fusiello,et al.  The bag of words approach for retrieval and categorization of 3D objects , 2010, The Visual Computer.

[28]  Alexei A. Efros,et al.  Data-driven visual similarity for cross-domain image matching , 2011, ACM Trans. Graph..

[29]  Thomas A. Funkhouser,et al.  Distinctive regions of 3D surfaces , 2007, TOGS.

[30]  Ariel Shamir,et al.  Filling Your Shelves: Synthesizing Diverse Style-Preserving Artifact Arrangements , 2014, IEEE Transactions on Visualization and Computer Graphics.

[31]  Alexei A. Efros,et al.  City Forensics: Using Visual Elements to Predict Non-Visual City Attributes , 2014, IEEE Transactions on Visualization and Computer Graphics.